[PATCH] swsusp: use non-contiguous memory on resume

The following patch is designed to fix a problem in the current implementation
of swsusp in mainline kernels.  Namely, swsusp uses an array of page backup
entries (aka pagedir) to store pointers to memory pages that must be saved
during suspend and restored during resume.

Unfortunately, the pagedir has to be located in a contiguous chunk of memory
and it sometimes turns out that an 8-order or even 9-order allocation is
needed for this purpose.  It sometimes is impossible to get such an allocation
and swsusp may fail during either suspend or resume due to the lack of memory,
although theoretically there is enough free memory for it to succeed.

Moreover, swsusp is more likely to fail for this reason during resume, which
means that it may fail during resume after a successful suspend (this actually
has happened for some people, including me :-)) and this, potentially, may
lead to the loss of data.

The problem is fixed by replacing the pagedir with a linklist so that
high-order memory allocations are avoided (the patches make swsusp use only
0-order allocations).  Unfortunately this means that it's necessary to change
assembly routines used to restore the image after it's been loaded from swap
so that they walk the list instead of walking the array.

This patch makes swsusp allocate only individual pages during resume.  it
contains the necessary changes to the assembly routines etc.  for i386 and
x86-64.
Signed-off-by: Rafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: Pavel Machek <pavel@suse.cz>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

arch/i386/kernel/asm-offsets.c

@@ -7,6 +7,7 @@
 #include <linux/sched.h>
 #include <linux/signal.h>
 #include <linux/personality.h>
+#include <linux/suspend.h>
 #include <asm/ucontext.h>
 #include "sigframe.h"
 #include <asm/fixmap.h>
@@ -56,6 +57,11 @@ void foo(void)
 
 	OFFSET(EXEC_DOMAIN_handler, exec_domain, handler);
 	OFFSET(RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext);
+	BLANK();
+
+	OFFSET(pbe_address, pbe, address);
+	OFFSET(pbe_orig_address, pbe, orig_address);
+	OFFSET(pbe_next, pbe, next);
 
 	/* Offset from the sysenter stack to tss.esp0 */
 	DEFINE(TSS_sysenter_esp0, offsetof(struct tss_struct, esp0) -

arch/i386/power/swsusp.S

@@ -12,6 +12,7 @@
 #include <linux/linkage.h>
 #include <asm/segment.h>
 #include <asm/page.h>
+#include <asm/asm_offsets.h>
 
 	.text
 
@@ -28,28 +29,28 @@ ENTRY(swsusp_arch_suspend)
 	ret
 
 ENTRY(swsusp_arch_resume)
-	movl $swsusp_pg_dir-__PAGE_OFFSET,%ecx
-	movl %ecx,%cr3
+	movl	$swsusp_pg_dir-__PAGE_OFFSET, %ecx
+	movl	%ecx, %cr3
 
-	movl	pagedir_nosave, %ebx
-	xorl	%eax, %eax
-	xorl	%edx, %edx
+	movl	pagedir_nosave, %edx
 	.p2align 4,,7
 
 copy_loop:
-	movl	4(%ebx,%edx),%edi
-	movl	(%ebx,%edx),%esi
+	testl	%edx, %edx
+	jz	done
+
+	movl	pbe_address(%edx), %esi
+	movl	pbe_orig_address(%edx), %edi
 
 	movl	$1024, %ecx
 	rep
 	movsl
 
-	incl	%eax
-	addl	$16, %edx
-	cmpl	nr_copy_pages,%eax
-	jb copy_loop
+	movl	pbe_next(%edx), %edx
+	jmp	copy_loop
 	.p2align 4,,7
 
+done:
 	movl saved_context_esp, %esp
 	movl saved_context_ebp, %ebp
 	movl saved_context_ebx, %ebx

arch/x86_64/kernel/asm-offsets.c

@@ -62,8 +62,8 @@ int main(void)
 	       offsetof (struct rt_sigframe32, uc.uc_mcontext));
 	BLANK();
 #endif
-	DEFINE(SIZEOF_PBE, sizeof(struct pbe));
 	DEFINE(pbe_address, offsetof(struct pbe, address));
 	DEFINE(pbe_orig_address, offsetof(struct pbe, orig_address));
+	DEFINE(pbe_next, offsetof(struct pbe, next));
 	return 0;
 }

arch/x86_64/kernel/suspend_asm.S

@@ -54,16 +54,10 @@ ENTRY(swsusp_arch_resume)
 	movq	%rax, %cr4;  # turn PGE back on
 
 	movq	pagedir_nosave(%rip), %rdx
-	/* compute the limit */
-	movl	nr_copy_pages(%rip), %eax
-	testl	%eax, %eax
-	jz	done
-	movq	%rdx,%r8
-	movl	$SIZEOF_PBE,%r9d
-	mul		%r9  # with rax, clobbers rdx
-	movq 	%r8, %rdx
-	addq	%r8, %rax
 loop:
+	testq	%rdx, %rdx
+	jz	done
+
 	/* get addresses from the pbe and copy the page */
 	movq	pbe_address(%rdx), %rsi
 	movq	pbe_orig_address(%rdx), %rdi
@@ -72,9 +66,8 @@ loop:
 	movsq
 
 	/* progress to the next pbe */
-	addq	$SIZEOF_PBE, %rdx
-	cmpq	%rax, %rdx
-	jb	loop
+	movq	pbe_next(%rdx), %rdx
+	jmp	loop
 done:
 	movl	$24, %eax
 	movl	%eax, %ds